PACED: Distillation at the Frontier of Student Competence
Paper • 2603.11178 • Published • 4
papers
-
-
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
Paper • 2603.12255 • Published • 91 -
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
Paper • 2603.12201 • Published • 53 -
TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 15